Skip to content
K

KAUSHIK DAS

AI Engineer &
Backend Engineer

/  Home/  Projects/  Knowledge/  AI Lab/  Writing/  Videos/  About

© 2026 Kaushik Das
Made with code & ☕

THEME

AI LAB / WHAT I INVESTIGATE

AI Lab

Experiments, benchmarks, failures, and reproducible conclusions.

08 EXPERIMENTS
EXP-014complete

RAG Retrieval on Local Models

RAG · Local AI · Benchmarks

Recall@5
91.4%
P95 latency
312ms
Queries
500
Aug 26, 2026VIEW RESULTS →
EXP-015complete

Agent Tools Under Failure

Agents · Evaluation · Reliability

Pass rate
86.4%
Unsafe retries
2.1%
Tests
120
Aug 21, 2026VIEW RESULTS →
EXP-016complete

Can LLMs Generate Schemas?

LLMs · Structured Output · Evaluation

First-pass valid
89.8%
After repair
97.5%
Runs
80
Aug 18, 2026VIEW RESULTS →
EXP-017complete

Semantic Cache Thresholds

Caching · Embeddings · Performance

Safe hit rate
41%
False reuse
0.7%
Pairs
900
Aug 12, 2026VIEW RESULTS →
EXP-018complete

Local Inference Routing

Local AI · Model Routing · Latency

Local route
58%
Quality delta
-1.8%
Cost saved
46%
Aug 6, 2026VIEW RESULTS →
EXP-019complete

Chunk Size vs Answer Quality

RAG · Chunking · Evaluation

Best recall
94.1%
Citation precision
90.7%
Documents
180
Jul 30, 2026VIEW RESULTS →
EXP-020complete

Reranker Latency Budget

RAG · Reranking · Performance

Best candidate count
20
Added P95
184ms
NDCG gain
+11.2%
Jul 22, 2026VIEW RESULTS →
EXP-021inconclusive

Streaming JSON Repair

LLMs · Streaming · Structured Output

Earlier useful data
420ms
Repair success
72%
Runs
200
Jul 14, 2026VIEW RESULTS →
8 EXPERIMENTS INDEXED ✓